Upload folder using huggingface_hub
Browse files- README.md +31 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- checkpoint_complete +0 -0
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- clawpathy
|
| 4 |
+
- tinker
|
| 5 |
+
- lora
|
| 6 |
+
- sft
|
| 7 |
+
base_model: Qwen/Qwen3-8B
|
| 8 |
+
library_name: tinker
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# clawpathy-4b-scriptwriting-reasoning
|
| 12 |
+
|
| 13 |
+
Trained with [Clawpathy](https://github.com/clawpathy) using the Tinker platform.
|
| 14 |
+
|
| 15 |
+
## Training Details
|
| 16 |
+
|
| 17 |
+
| Parameter | Value |
|
| 18 |
+
|---|---|
|
| 19 |
+
| **Base model** | Qwen/Qwen3-8B |
|
| 20 |
+
| **Method** | Supervised Fine-Tuning |
|
| 21 |
+
| **Dataset** | MuratcanKoylan/impossible-moments |
|
| 22 |
+
| **LoRA rank** | 32 |
|
| 23 |
+
| **Learning rate** | 0.00024000000000000003 |
|
| 24 |
+
| **Steps** | 200 |
|
| 25 |
+
| **Final loss** | 0.617072 |
|
| 26 |
+
| **Tinker sampler path** | `tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/sampler_weights/clawpathy-2797142f-590-final` |
|
| 27 |
+
| **Tinker state path** | `tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/weights/clawpathy-2797142f-590-state` |
|
| 28 |
+
|
| 29 |
+
## Evaluation
|
| 30 |
+
|
| 31 |
+
No evaluation results available.
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": null,
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 32,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": "all-linear",
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"trainable_token_indices": null,
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15924ef0ba3c57c9b049316a32615bbefb84bab8222618f33f3745860d83f011
|
| 3 |
+
size 369216072
|
checkpoint_complete
ADDED
|
File without changes
|